Last active
July 13, 2019 01:05
-
-
Save daxiongshu/d46a45d22c167419964f71f22315148c to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"(200000, 202)\n" | |
] | |
} | |
], | |
"source": [ | |
"import cudf as gd\n", | |
"import pandas as pd\n", | |
"import time\n", | |
"import xgboost as xgb\n", | |
"import warnings\n", | |
"warnings.filterwarnings(\"ignore\")\n", | |
"\n", | |
"PATH = '../input'\n", | |
"cols = ['ID_code', 'target'] + ['var_%d'%i for i in range(200)]\n", | |
"dtypes = ['int32', 'int32'] + ['float32' for i in range(200)]\n", | |
"train_gd = gd.read_csv('%s/train.csv'%PATH,names=cols,dtype=dtypes,skiprows=1)\n", | |
"print(train_gd.shape)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train,valid = train_gd[:-10000],train_gd[-10000:]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"x_train = train.drop(['target','ID_code'])\n", | |
"y_train = train['target']\n", | |
"x_valid = valid.drop(['target','ID_code'])\n", | |
"y_valid = valid['target']" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"CPU times: user 9.17 s, sys: 1.68 s, total: 10.9 s\n", | |
"Wall time: 1.8 s\n" | |
] | |
} | |
], | |
"source": [ | |
"%%time\n", | |
"xgb_params = {\n", | |
" 'objective': 'binary:logistic',\n", | |
" 'tree_method': 'gpu_hist',\n", | |
" 'max_depth': 1, \n", | |
" 'eta':0.1,\n", | |
" 'silent':1,\n", | |
" 'subsample':0.5,\n", | |
" 'colsample_bytree': 0.05, \n", | |
" 'eval_metric':'auc',\n", | |
"}\n", | |
"dtrain = xgb.DMatrix(data=x_train.to_pandas(), label=y_train.to_pandas())\n", | |
"dvalid = xgb.DMatrix(data=x_valid.to_pandas(), label=y_valid.to_pandas())" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"[0]\teval-auc:0.523106\ttrain-auc:0.524118\n", | |
"Multiple eval metrics have been passed: 'train-auc' will be used for early stopping.\n", | |
"\n", | |
"Will train until train-auc hasn't improved in 30 rounds.\n", | |
"[1000]\teval-auc:0.877147\ttrain-auc:0.886773\n", | |
"[2000]\teval-auc:0.889509\ttrain-auc:0.90243\n", | |
"[3000]\teval-auc:0.89368\ttrain-auc:0.907889\n", | |
"[4000]\teval-auc:0.895291\ttrain-auc:0.910346\n", | |
"Stopping. Best iteration:\n", | |
"[4876]\teval-auc:0.895474\ttrain-auc:0.911888\n", | |
"\n" | |
] | |
} | |
], | |
"source": [ | |
"watchlist = [(dvalid, 'eval'), (dtrain, 'train')]\n", | |
"clf = xgb.train(xgb_params, dtrain=dtrain,\n", | |
" num_boost_round=10000,evals=watchlist,\n", | |
" early_stopping_rounds=30,maximize=True,\n", | |
" verbose_eval=1000)\n", | |
"yp = clf.predict(dvalid)" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.6.8" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment